jarvisss
Browse files- README.md +55 -0
- config.json +71 -0
- model.safetensors +3 -0
- runs/Apr24_13-23-12_ZaksMSI/events.out.tfevents.1713982994.ZaksMSI.19144.0 +3 -0
- runs/Apr24_13-23-32_ZaksMSI/events.out.tfevents.1713983013.ZaksMSI.19144.1 +3 -0
- special_tokens_map.json +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert/distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: results
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# results
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 2e-05
|
36 |
+
- train_batch_size: 1
|
37 |
+
- eval_batch_size: 1
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 1
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
46 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
47 |
+
| No log | 1.0 | 18 | 3.0936 | 0.3333 |
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.39.3
|
53 |
+
- Pytorch 2.2.2+cpu
|
54 |
+
- Datasets 2.19.0
|
55 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "28",
|
13 |
+
"1": "Audi",
|
14 |
+
"2": "Bohemian Rhapsody",
|
15 |
+
"3": "Breaking Bad",
|
16 |
+
"4": "Christmas",
|
17 |
+
"5": "Diving",
|
18 |
+
"6": "England",
|
19 |
+
"7": "Erica Heon's Pizza",
|
20 |
+
"8": "Harry Potter",
|
21 |
+
"9": "Interstellar",
|
22 |
+
"10": "London",
|
23 |
+
"11": "Mac",
|
24 |
+
"12": "Minecraft",
|
25 |
+
"13": "Monster Energy Drink",
|
26 |
+
"14": "Playstation",
|
27 |
+
"15": "Programming",
|
28 |
+
"16": "Purple & Gold **geaux tigers**",
|
29 |
+
"17": "Tex & Kylie",
|
30 |
+
"18": "The Beatles",
|
31 |
+
"19": "Zak 'The Man' Rowton",
|
32 |
+
"20": "iPhone"
|
33 |
+
},
|
34 |
+
"initializer_range": 0.02,
|
35 |
+
"label2id": {
|
36 |
+
"28": 0,
|
37 |
+
"Audi": 1,
|
38 |
+
"Bohemian Rhapsody": 2,
|
39 |
+
"Breaking Bad": 3,
|
40 |
+
"Christmas": 4,
|
41 |
+
"Diving": 5,
|
42 |
+
"England": 6,
|
43 |
+
"Erica Heon's Pizza": 7,
|
44 |
+
"Harry Potter": 8,
|
45 |
+
"Interstellar": 9,
|
46 |
+
"London": 10,
|
47 |
+
"Mac": 11,
|
48 |
+
"Minecraft": 12,
|
49 |
+
"Monster Energy Drink": 13,
|
50 |
+
"Playstation": 14,
|
51 |
+
"Programming": 15,
|
52 |
+
"Purple & Gold **geaux tigers**": 16,
|
53 |
+
"Tex & Kylie": 17,
|
54 |
+
"The Beatles": 18,
|
55 |
+
"Zak 'The Man' Rowton": 19,
|
56 |
+
"iPhone": 20
|
57 |
+
},
|
58 |
+
"max_position_embeddings": 512,
|
59 |
+
"model_type": "distilbert",
|
60 |
+
"n_heads": 12,
|
61 |
+
"n_layers": 6,
|
62 |
+
"pad_token_id": 0,
|
63 |
+
"problem_type": "single_label_classification",
|
64 |
+
"qa_dropout": 0.1,
|
65 |
+
"seq_classif_dropout": 0.2,
|
66 |
+
"sinusoidal_pos_embds": false,
|
67 |
+
"tie_weights_": true,
|
68 |
+
"torch_dtype": "float32",
|
69 |
+
"transformers_version": "4.39.3",
|
70 |
+
"vocab_size": 30522
|
71 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a61f587e95108babe0709e23e9371ded6e82210f553dc6e7d00d6eefff01aa7
|
3 |
+
size 267891012
|
runs/Apr24_13-23-12_ZaksMSI/events.out.tfevents.1713982994.ZaksMSI.19144.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca849576dba9ec64dfd5026d6442091e05047a7bce65f0f0e4985aa851b8cfc9
|
3 |
+
size 6166
|
runs/Apr24_13-23-32_ZaksMSI/events.out.tfevents.1713983013.ZaksMSI.19144.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8387a393cd3c006788712c78f3c3ec77bf4f425ff6fccc477ba9487ef54b1f4c
|
3 |
+
size 6166
|
special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": {
|
5 |
+
"content": "[PAD]",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 1000000000000000019884624838656,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ec0df6e43cdbce213b3df1be91eb19494728cc7b123e6dee802e7f09444cc3c
|
3 |
+
size 4920
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|